Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
router-qwen2.5-7b-dpo-v1.00 – AI Model by taixingbi | AlphaNeural AI
You can deploy this model and start earning money today!
taixingbi
/
router-qwen2.5-7b-dpo-v1.00
like
0
peft
safetensors
text-generation
conversational
Qwen/Qwen2.5-7B-Instruct
adapter
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
taixingbi/router-qwen2.5-7b-dpo-v1.00
LoRA adapter from HuntAI router DPO training (
layer-router-train-v1
).
Base model:
Qwen/Qwen2.5-7B-Instruct
Load with PEFT / vLLM
--enable-lora
.
Training timing
Metric
Value
Train time
229.71s
Samples/sec
0.209
Steps/sec
0.026
Global step
6
